New LM-GNN Framework Enhances Clinical Prediction with Patient Cohort Insights

Researchers have developed a novel framework called Patients-like-me (PLM) that combines language models (LMs) and graph neural networks (GNNs) for improved clinical prediction using electronic health records (EHRs). This integrated approach leverages the semantic understanding of LMs for individual patient data and the relational insights from GNNs across patient cohorts. PLM utilizes a Variational Expectation-Maximization algorithm for efficient training and has demonstrated superior performance on the MIMIC-III and MIMIC-IV datasets compared to existing methods. AI

IMPACT This framework could lead to more accurate and explainable clinical predictions by better utilizing patient data relationships.

RANK_REASON The cluster describes a new research paper detailing a novel framework for clinical prediction. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Ehrs
• graph neural networks
• LM--GNN
• MIMIC-III
• MIMIC-IV

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →